arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2101.00797cs.LGcs.SI
收藏

图卷积网络中的超低频信息

Beyond Low-frequency Information in Graph Convolutional Networks

Beijing University of Posts and Telecommunications(北京邮电大学);Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所)

Deyu Bo, Xiao Wang, Chuan Shi, Huawei Shen

摘要:

图神经网络(GNN)已被证明在各种网络相关任务中是有效的。大多数现有的GNN通常利用节点特征的低频信号,这引发了一个基本问题:低频信息是否就是我们在现实世界中所需要的全部信息?在本文中,我们首先提出了一个实验研究评估低频和高频信号的作用,结果清楚地表明,探索低频信号是远离学习有效的节点表示在不同的情况下。我们如何自适应地学习GNN中低频信息之外的更多信息?一个明智的答案可以帮助GNN增强适应性。针对这一问题,提出了一种新的频率自适应图卷积网络(FAGCN),它具有自选通机制,能够在消息传递过程中自适应地融合不同的信号。为了更深入地理解,我们从理论上分析了低频信号和高频信号对学习节点表示的作用,这进一步解释了为什么FAGCN可以在不同类型的网络上表现良好。在六个真实网络上的大量实验验证了FAGCN不仅解决了过度平滑问题,而且具有优于现有技术的优势。

英文摘要:

Graph neural networks (GNNs) have been proven to be effective in various network-related tasks. Most existing GNNs usually exploit the low-frequency signals of node features, which gives rise to one fundamental question: is the low-frequency information all we need in the real world applications? In this paper, we first present an experimental investigation assessing the roles of low-frequency and high-frequency signals, where the results clearly show that exploring low-frequency signal only is distant from learning an effective node representation in different scenarios. How can we adaptively learn more information beyond low-frequency information in GNNs? A well-informed answer can help GNNs enhance the adaptability. We tackle this challenge and propose a novel Frequency Adaptation Graph Convolutional Networks (FAGCN) with a self-gating mechanism, which can adaptively integrate different signals in the process of message passing. For a deeper understanding, we theoretically analyze the roles of low-frequency signals and high-frequency signals on learning node representations, which further explains why FAGCN can perform well on different types of networks. Extensive experiments on six real-world networks validate that FAGCN not only alleviates the over-smoothing problem, but also has advantages over the state-of-the-arts.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑